A Measure for Residual Correlation with Whiteness Test and Information Entropy

Correlation analysis on residuals is a classical checking method for dynamic stochastic modeling. By fusing information entropy and residual correlation in dynamic model analysis, the paper presents a new approach of model checking based on whiteness test and information entropy, and proposes a new diagnostic quantity named "residual entropy", which indicates the amount of information left in residual series. On normal distribution hypothesis about residuals, the paper gives the estimation expressions of residual entropy, and illustrates its application. The result of experiment shows that residual entropy is a useful diagnostic quantity in stochastic modeling. Performance comparison with the conventional methods indicates that minimum residual entropy can be applied as an effective checking criterion